markpdfdown

What it is

MarkPDFDown is a tool that leverages multimodal large language models to transcribe PDF files into Markdown format.

How it works

It processes PDFs (and images) into Markdown, preserving formatting such as headings, lists, and tables, and supports multiple LLM providers via LiteLLM. The project has a modular architecture with core components for LLM interaction and file processing.

Getting started

Installation (Using uv, recommended):

# Install uv if you haven't already
curl -LsSf https://astral.sh/uv/install.sh | sh

# Clone the repository
git clone https://github.com/MarkPDFdown/markpdfdown.git
cd markpdfdown

# Install dependencies and create virtual environment
uv sync

# Install the package in development mode
uv pip install -e .

Installation (Using conda):

conda create -n markpdfdown python=3.9
conda activate markpdfdown

# Clone the repository
git clone https://github.com/MarkPDFdown/markpdfdown.git
cd markpdfdown

# Install dependencies
pip install -e .

Usage (examples):

# Basic conversion
markpdfdown --input document.pdf --output output.md

# Convert specific page range
markpdfdown --input document.pdf --output output.md --start 1 --end 10

# Convert image to markdown
markpdfdown --input image.png --output output.md

# Using python module
python -m markpdfdown --input document.pdf --output output.md

Advanced usage and Docker are documented in the README for multi-file processing and containerized runs.

Recent releases

• 1.2.0 (2026-01-25): MarkPDFdown Desktop Version is now available!!!
• 1.1.2 (2025-09-20): Bug Fixes (CI build adjustments)
• 1.1.1 (2025-09-20): Bug Fixes
• 1.1.0 (2025-09-20): Refactors with litellm introduction
• 1.0.11 (2025-09-02): New Features ( multilingual README translations )

Traction

stars_7d: not provided stars_1d: not provided

Behind the repo

Linked desktop app repository: https://github.com/MarkPDFdown/markpdfdown-desktop

Caveats

License: Apache-2.0 Created: 2025-03-14 Last push: 2026-01-25 Open issues: 7